CN111442489B

CN111442489B - Control method and system of air conditioner, air conditioner and readable storage medium

Info

Publication number: CN111442489B
Application number: CN202010228854.0A
Authority: CN
Inventors: 方兴; 李元阳; 阎杰; 梁锐
Original assignee: GD Midea Heating and Ventilating Equipment Co Ltd; Shanghai Meikong Smartt Building Co Ltd
Current assignee: GD Midea Heating and Ventilating Equipment Co Ltd; Shanghai Meikong Smartt Building Co Ltd
Priority date: 2020-03-27
Filing date: 2020-03-27
Publication date: 2021-12-14
Anticipated expiration: 2040-03-27
Also published as: CN111442489A

Abstract

The invention provides a control method and a control system of air conditioning equipment, the air conditioning equipment and a readable storage medium, wherein the control method of the air conditioning equipment comprises the following steps: acquiring operating parameters of air conditioning equipment; inputting the operation parameters into a threshold value determination model to obtain target threshold values corresponding to the operation parameters; and determining a corresponding operation instruction according to the operation parameter and the target threshold value, and controlling the air conditioning equipment to execute the operation instruction. According to the technical scheme provided by the invention, the threshold value determination model is set, the target threshold value matched with the actual working condition of the air conditioning equipment is determined by taking the real-time operation parameters of the air conditioning equipment as the basis through the threshold value determination model, and the operation of the air conditioning equipment is controlled through the matched target threshold value, so that the control process of the air conditioning equipment is more consistent with the actual operation working condition of the air conditioning equipment, the operation control effect of the air conditioning equipment is further effectively improved, the operation stability of the air conditioning equipment is improved on one hand, and the operation energy efficiency coefficient of the air conditioning equipment is effectively improved on the other hand.

Description

Control method and system of air conditioner, air conditioner and readable storage medium

Technical Field

The present invention relates to the field of air conditioning equipment technology, and in particular, to a control method of air conditioning equipment, a control system of air conditioning equipment, and a computer-readable storage medium.

Background

In the related art, the central air conditioning system needs to perform loading and unloading control on the number of operating units during operation, so that the energy efficiency coefficient of the central air conditioning system is kept at a good level. The load increasing and reducing control usually adopts a current control method, namely, a load increasing and reducing threshold value of a current load rate is set in advance in a control system, and whether the load is required to be loaded or unloaded is judged by comparing the running current of the unit with the threshold value.

The loading and unloading threshold values are preset according to theoretical working conditions when the air conditioning unit leaves a factory, and in actual operation, if the working conditions of the unit change, the preset loading and unloading threshold values may not meet the actual working conditions, so that the loading and unloading are not timely, the loading and unloading cannot be carried out, or the situations of early loading, late unloading and the like occur, so that energy waste is caused, and the normal operation of the air conditioning equipment is influenced.

Disclosure of Invention

The present invention is directed to solving at least one of the problems of the prior art or the related art.

To this end, a first aspect of the present invention proposes a control method of an air conditioning apparatus.

A second aspect of the invention proposes a control system of an air conditioning apparatus.

A third aspect of the invention proposes an air conditioning apparatus.

A fourth aspect of the present invention is directed to a computer-readable storage medium.

In view of this, a first aspect of the present invention provides a control method of an air conditioning apparatus, including: acquiring operating parameters of air conditioning equipment; inputting the operation parameters into a threshold value determination model to obtain target threshold values corresponding to the operation parameters; and determining a corresponding operation instruction according to the operation parameter and the target threshold value, and controlling the air conditioning equipment to execute the operation instruction.

In the technical scheme, in the operation process of the air conditioning equipment, the operation parameters of the air conditioning equipment are obtained in real time, the operation parameters are analyzed through a threshold determination model to determine the actual working condition conditions of the current air conditioning equipment, the corresponding target threshold is determined according to the actual working condition conditions, the corresponding operation instructions, such as loading instructions or unloading instructions, are determined according to the real-time operation parameters and the target threshold which is consistent with the current working condition, and the air conditioning equipment is controlled to execute the corresponding control instructions.

According to the technical scheme provided by the invention, the threshold value determination model is set, the target threshold value matched with the actual working condition of the air conditioning equipment is determined by the threshold value determination model on the basis of the real-time operation parameters of the air conditioning equipment, and the operation of the air conditioning equipment is controlled by the matched target threshold value, so that the control process of the air conditioning equipment is more consistent with the actual operating working condition of the air conditioning equipment, the operation control effect of the air conditioning equipment is further effectively improved, the operation stability of the air conditioning equipment is improved, the load can be timely increased and reduced, and the operation energy consumption coefficient of the air conditioning equipment is effectively improved.

In addition, the operation control method of the air conditioning equipment in the above technical solution provided by the present invention may further have the following additional technical features:

in the technical scheme, the operation parameters comprise the current load rate of the air conditioning equipment, and the target threshold comprises a maximum load rate threshold and a minimum load rate threshold corresponding to the current load rate; determining a corresponding operation instruction according to the operation parameter and the target threshold, specifically comprising: identifying the magnitude relation between the current load rate and the maximum load rate and the minimum load rate; recognizing that the current load rate is greater than or equal to the maximum load rate threshold value, and determining the operation instruction as a loading operation; and recognizing that the current load rate is less than or equal to the minimum load rate threshold value, and determining the operation command as load shedding operation.

In the technical scheme, the target threshold comprises a maximum load rate threshold and a minimum load rate threshold corresponding to the current load rate, and the corresponding operation instruction is determined according to the comparison result of the current load rate of the rear water cooling unit in the air conditioning equipment, which is obtained in real time, and the maximum load rate threshold and the minimum load rate threshold. Specifically, if the current load rate is greater than or equal to the maximum load rate threshold, it indicates that the current air conditioning load is increased, and at this time, it is determined that the operation instruction is a loading operation, and the air conditioning equipment is controlled to load more units, so as to ensure the cooling effect. If the current load rate is smaller than or equal to the minimum load rate threshold value, the current air conditioner load is reduced, the operation instruction is determined to be load reduction operation at the moment, and the number of the running units is controlled to be reduced, so that the energy efficiency of the system is improved.

In any of the above technical solutions, the operation parameters further include an inlet water temperature of chilled water of a water cooling unit of the air conditioning equipment and an outlet water temperature of the chilled water, and the target threshold further includes a first difference threshold, a second difference threshold, and a third difference threshold; before the step of identifying the magnitude relationship between the current load rate and the maximum load rate and the minimum load rate, the operation control method further includes; obtaining the set outlet water temperature of the chilled water; calculating a first difference value between the water temperature and the set water outlet temperature, and calculating a second difference value between the water inlet temperature and the water outlet temperature; determining that the absolute value of the first difference is less than a first difference threshold or the second difference is greater than a second difference threshold; or determining that the absolute value of the first difference is less than the first difference threshold and the second difference is less than the third difference threshold, and performing the step of identifying the magnitude relationship between the current load rate and the maximum load rate and the minimum load rate.

In the technical scheme, the operation parameters further comprise the water inlet temperature and the water outlet temperature of the chilled water of the air conditioning equipment, and before the loading operation or the unloading operation is determined according to the current load factor, whether the cooling capacity or the heating capacity of the air conditioning equipment meets the cooling capacity or the heating capacity required by a user or not is judged according to the water inlet temperature and the water outlet temperature. Specifically, a first difference between the water temperature and the set outlet water temperature is calculated, and the first difference can reflect whether the actual cooling load of the current water chilling unit exceeds the rated load of the current water chilling unit.

Specifically, the step of identifying the magnitude relation of the current load rate to the maximum load rate and the minimum load rate is performed when either one of the first difference value greater in absolute value than the first difference threshold or the second difference value greater than the second difference threshold is satisfied, or the step of identifying the magnitude relation of the current load rate to the maximum load rate and the minimum load rate is performed when both the first difference value less in absolute value than the first difference threshold and the second difference value less than the third difference threshold are satisfied.

In any of the above technical solutions, the operation control method of the air conditioning equipment further includes: and acquiring a setting instruction, and determining a first difference threshold, a second difference threshold and a third difference threshold according to the setting instruction.

In the technical scheme, the first difference threshold, the second difference threshold and the third difference threshold can be specifically set according to actual parameters and working environment of the air conditioning equipment. When the operating environment of the air conditioning equipment is changed, or the user requirement is changed, or the air conditioning equipment is modified, the first difference threshold value, the second difference threshold value and the third difference threshold value can be manually modified by sending a setting instruction to the air conditioning system so as to ensure that the operation control of the air conditioning equipment can always meet the actual adaptive environment and ensure the operation effect of the air conditioning equipment.

In any of the above technical solutions, the operation control method of the air conditioning equipment further includes: acquiring a preset model and acquiring historical operating parameters; and generating a corresponding training set according to the historical operating parameters, and training a preset model through the training set to obtain a threshold determination model.

In the technical scheme, the threshold determination model is obtained by training the artificial intelligent model through big data, and the accuracy of the generated target threshold is improved in the subsequent control process. Specifically, historical operating parameters can be obtained in a database, the operating parameters of the water cooling unit of the air conditioning equipment under a large number of different configurations, different use scenes and different working condition environments are included, the parameters are processed to generate corresponding training sets, and the preset models are trained through the training sets, so that the finally obtained threshold value determining models are more accurate and are close to the operating state of the actual equipment, and the operation control effect of the air conditioning equipment is improved.

In any of the above technical solutions, the step of generating a corresponding training set according to the historical operating parameters specifically includes: performing data cleaning on the historical operating parameters to obtain a noise reduction data set; and marking the noise reduction data set through a mean shift clustering algorithm to obtain a training set.

In the technical scheme, since the historical operating parameters may include operating data in an abnormal state, such as fault operating data of air conditioning equipment, zero drift data generated by a sensor, data loss generated in a network transmission process, and the like, in order to improve the accuracy of the threshold determination model, data cleaning needs to be performed on the historical operating parameters to remove noise data in the data. Meanwhile, after the noise reduction data set is obtained, the noise reduction data set is marked through a mean shift clustering algorithm, a training set for training a preset model can be obtained, the accuracy of the threshold value determination model can be effectively improved through training the preset model through the training set, and further the operation control effect of the air conditioning equipment is improved.

In any of the above technical solutions, the step of performing data cleaning on the historical operating parameters specifically includes: sequencing the historical operating parameters to obtain a historical operating parameter sequence; determining a target parameter interval according to the historical operating parameter sequence, acquiring historical operating parameters in the target parameter interval, and determining the historical operating parameters as a first data set; filling the first data set by a hot card filling method to obtain a second data set; and determining the working condition characteristics corresponding to each historical operating parameter in the second data set, acquiring the historical operating parameters corresponding to the working condition characteristics which accord with the preset working condition characteristics in the second data set, and determining the historical operating parameters as a noise reduction data set.

In the technical scheme, the data cleaning of the historical operating parameters can be divided into the following steps:

first, outlier culling is performed. Specifically, the historical operating parameters of the same category are sorted according to the numerical value, the operating parameter sequence arranged according to the numerical value is obtained, the target parameter interval is determined according to the operating parameter sequence, the upper quartile value and the lower quartile value of the operating parameter sequence can be calculated, the upper quartile value and the lower quartile value serve as boundary values to determine the upper boundary and the lower boundary of the target parameter interval, and when the operating parameters exceed the upper boundary and the lower boundary of the target operating parameters, data abnormality is judged. In the operation process, conditions such as system faults, sensor drift and the like can possibly cause abnormal large values and abnormal small values of operation parameters, so that after the data are removed, a first data set of the operation parameters which can reflect normal operation conditions can be obtained.

In the second step, missing value supplementation is performed on the first data set after the outlier is proposed. Specifically, if the first data set has missing necessary data, a historical parameter closest to a working condition of a missing value is searched in a unit historical operation database through a hot card filling method, and the missing value is supplemented through the historical parameter, so that a second data set with better integrity is obtained.

And thirdly, screening the second data set under stable working conditions. Specifically, the working condition characteristics corresponding to each historical operating parameter in the second data set are determined, and whether the working condition characteristics meet preset working conditions or not is judged. In the operation process of the air conditioning equipment, extreme operation conditions such as start-stop process and the like can occur, and the corresponding working condition is unstable, so that only the historical operation parameters of the second data set under the stable working condition are obtained, and the training set is generated according to the operation parameters, so that the accuracy and the precision of the threshold value determination model can be effectively ensured, and the operation control effect of the air conditioning equipment is further ensured.

In any of the above technical solutions, the step of marking the noise reduction data set by using a mean shift clustering algorithm specifically includes: selecting any historical operating parameter from the noise reduction data set, and determining the parameter as first initial central data; acquiring a preset kernel function and an updating function, and acquiring a function bandwidth corresponding to the preset kernel function; calculating a first offset mean value corresponding to the first initial central data through a preset kernel function, and identifying the size relation between the first offset mean value and a preset offset threshold value; determining that the first deviation mean value is larger than or equal to a preset deviation threshold value, determining second initial central data through an updating function, determining a second deviation mean value corresponding to the second initial central data through a preset kernel function, and determining the second central data as central data until the second deviation mean value is smaller than the preset deviation threshold value; and determining a target data category to which the central data belongs, and marking the historical operating parameters with the difference value smaller than or equal to the function bandwidth with the central data as the target data category.

In the technical scheme, in the process of marking the noise reduction data set by the mean shift clustering algorithm, the preset kernel function can be processed by adopting a three-dimensional kernel function such as a Gaussian kernel function. Specifically, a historical operating parameter is selected from the noise reduction data set as first initial central data, a function bandwidth of a preset kernel function is used as a radius, a set of the historical operating parameter is divided, and a first deviation mean value corresponding to the first central data is determined according to the set of the historical operating parameter. The first deviation mean value can reflect the difference between the first initial central data and other historical operating parameters, and the larger the first deviation value, the farther the first initial central data is from the actual data "center".

Therefore, if the first deviation mean value is larger than the preset deviation threshold value, it is indicated that the current first initial central data is not properly selected, at this time, the next historical operating parameter is determined through the updating function and is used as the second initial central data, until the second deviation mean value corresponding to one historical operating parameter is found to be smaller than the preset deviation mean value, it is indicated that the historical operating parameter is located at the center point of the most dense data point, the historical operating parameter is determined as the central data, and the target data category to which the central data belongs is determined.

After the central data and the target data category of the central data are determined, a data set is divided by taking the central data as a circle center and the function bandwidth as a radius, all historical operating parameters in the set are marked as the target data category which is the same as the central data, and thus, the marking of a group of training sets is completed.

In any of the above solutions, the historical operating parameters include a compressor current load rate of the air conditioning equipment, and at least one of: the running state of a water chilling unit of the air conditioning equipment, the outlet water temperature of cooling water of the air conditioning equipment, the inlet water temperature of the cooling water of the air conditioning equipment, the outlet water temperature of chilled water of the air conditioning equipment and the return water temperature of the chilled water of the air conditioning equipment.

In the technical scheme, the historical operating parameters include a compressor current load rate of the air conditioner, an operating state of a water chilling unit of the air conditioner, a cooling water outlet temperature of the air conditioner, a cooling water inlet temperature of the air conditioner, a chilled water outlet temperature of the air conditioner, a chilled water return temperature of the air conditioner and the like, and it can be understood that the historical operating parameters may further include any other operating parameters which can be acquired and correspond to the air conditioner in operation along with different air conditioners.

A second aspect of the present invention provides an operation control system of an air conditioning apparatus, including: a memory configured to store a computer program; the processor is configured to execute the computer program to implement the operation control method of the air conditioning equipment provided in any one of the above technical solutions, and therefore, the operation control system of the air conditioning equipment includes all the beneficial effects of the operation control method of the air conditioning equipment provided in any one of the above technical solutions, which are not described herein again.

A third aspect of the present invention provides an air conditioning apparatus comprising: the water cooling units comprise compressors, cooling water pipes, heat exchangers and throttling devices; the detection device is configured to acquire the current load rate of the compressor, acquire the water inlet temperature and the water outlet temperature of the cooling water pipe and acquire the water inlet temperature and the water outlet temperature of the freezing water pipe; according to the operation control system of the air conditioning equipment provided by any one of the technical schemes, the operation control system of the air conditioning equipment is connected with the water cooling unit and the detection device. Therefore, the air conditioning equipment includes all the advantages of the operation control system of the air conditioning equipment provided in any one of the above technical solutions, and details are not repeated herein.

A fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the operation control method for an air conditioning device provided in any one of the above technical solutions, and therefore, the computer-readable storage medium includes all the beneficial effects of the operation control method for an air conditioning device provided in any one of the above technical solutions, and is not described herein again.

Drawings

The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 illustrates a flowchart of a control method of an air conditioner according to an embodiment of the present invention;

fig. 2 illustrates another flowchart of a control method of an air conditioner according to an embodiment of the present invention;

fig. 3 illustrates still another flowchart of a control method of an air conditioner according to an embodiment of the present invention;

fig. 4 is still another flowchart illustrating a control method of an air conditioner according to an embodiment of the present invention;

fig. 5 is still another flowchart illustrating a control method of an air conditioner according to an embodiment of the present invention;

fig. 6 is a schematic diagram illustrating a principle of mean shift clustering in a control method of an air conditioner according to an embodiment of the present invention;

fig. 7 is still another flowchart illustrating a control method of an air conditioner according to an embodiment of the present invention;

fig. 8 is a data diagram illustrating a clustering result in a control method of an air conditioner according to an embodiment of the present invention;

fig. 9 is a data diagram showing a threshold model in a control method of an air conditioner according to an embodiment of the present invention;

fig. 10 is a block diagram showing a configuration of a control system of an air conditioner according to an embodiment of the present invention.

Detailed Description

In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.

An operation control method of an air conditioner, an operation control system of an air conditioner, and a computer-readable storage medium according to some embodiments of the present invention are described below with reference to fig. 1 to 10.

Example one

As shown in fig. 1, in one embodiment of the present invention, there is provided a control method of an air conditioning apparatus, including:

step S102, obtaining operation parameters of air conditioning equipment;

step S104, inputting the operation parameters into a threshold value determination model to obtain target threshold values corresponding to the operation parameters;

and S106, determining a corresponding operation instruction according to the operation parameter and the target threshold value, and controlling the air conditioning equipment to execute the operation instruction.

The operation parameters comprise the current load rate of the air conditioning equipment, and the target threshold comprises a maximum load rate threshold and a minimum load rate threshold corresponding to the current load rate; as shown in fig. 2, the step of determining the corresponding operation instruction according to the operation parameter and the target threshold specifically includes:

step S202, identifying the magnitude relation between the current load rate and the maximum load rate and the minimum load rate;

step S204, recognizing that the current load rate is greater than or equal to the maximum load rate threshold value, and determining an operation instruction as a loading operation;

and step S206, recognizing that the current load rate is less than or equal to the minimum load rate threshold value, and determining the operation command as load shedding operation.

The operation parameters further comprise the inlet water temperature of cooling water of the air conditioning equipment and the outlet water temperature of the cooling water, and the target threshold further comprises a first difference threshold, a second difference threshold and a third difference threshold; before the step of identifying the magnitude relationship between the current load rate and the maximum load rate and the minimum load rate, the operation control method further includes:

acquiring a set water outlet temperature; calculating a first difference value between the water temperature and the set water outlet temperature, and calculating a second difference value between the water inlet temperature and the water outlet temperature; determining that the absolute value of the first difference is less than a first difference threshold or the second difference is greater than a second difference threshold; or determining that the absolute value of the first difference is less than the first difference threshold and the second difference is less than the third difference threshold, and performing the step of identifying the magnitude relationship between the current load rate and the maximum load rate and the minimum load rate.

The operation control method of the air conditioning apparatus further includes: and acquiring a setting instruction, and determining a first difference threshold, a second difference threshold and a third difference threshold according to the setting instruction.

In this embodiment, in the operation process of the air conditioning equipment, the operation parameters of the air conditioning equipment are obtained in real time, the operation parameters are analyzed through the threshold determination model to determine the actual working condition conditions of the current air conditioning equipment, the corresponding target threshold is determined according to the actual working condition conditions, the corresponding operation instruction, such as a loading instruction or an unloading instruction, is determined according to the real-time operation parameters and the target threshold conforming to the current working condition, and the air conditioning equipment is controlled to execute the corresponding control instruction.

The target threshold comprises a maximum load rate threshold and a minimum load rate threshold corresponding to the current load rate, and the corresponding operation instruction is determined according to the comparison result of the current load rate of the air conditioning equipment, which is acquired in real time, and the maximum load rate threshold and the minimum load rate threshold.

Specifically, if the current load rate is greater than or equal to the maximum load rate threshold, it indicates that the current air conditioning load is increased, and at this time, it is determined that the operation instruction is a loading operation, and the air conditioning equipment is controlled to load more units, so as to ensure the cooling effect. If the current load rate is smaller than or equal to the minimum load rate threshold value, the current air conditioner load is reduced, the operation instruction is determined to be load reduction operation at the moment, and the air conditioner is controlled to reduce the running unit, so that the energy efficiency is improved.

The operation parameters also comprise the water inlet temperature and the water outlet temperature of the chilled water of the air conditioning equipment, and before the loading operation or the unloading operation is determined according to the current load rate, whether the cooling capacity or the heating capacity of the air conditioning equipment meets the cooling capacity or the heating capacity required by a user or not is judged according to the water inlet temperature and the water outlet temperature. Specifically, a first difference between the water temperature and the set outlet water temperature is calculated, wherein the first difference is calculated.

The first difference threshold, the second difference threshold and the third difference threshold can be specifically set according to actual parameters and working environments of the air conditioning equipment. When the operating environment of the air conditioning equipment is changed, or the user requirement is changed, or the air conditioning equipment is modified, the first difference threshold value, the second difference threshold value and the third difference threshold value can be manually modified by sending a setting instruction to the air conditioning system so as to ensure that the operation control of the air conditioning equipment can always meet the actual adaptive environment and ensure the operation effect of the air conditioning equipment.

According to the embodiment provided by the invention, the threshold value determination model is set, the target threshold value matched with the actual working condition of the air conditioning equipment is determined by the threshold value determination model on the basis of the real-time operation parameters of the air conditioning equipment, and the operation of the air conditioning equipment is controlled by the matched target threshold value, so that the control process of the air conditioning equipment is more consistent with the actual operating working condition of the air conditioning equipment, the operation control effect of the air conditioning equipment is further effectively improved, the operation stability of the air conditioning equipment is improved on one hand, and the operation energy efficiency coefficient of the air conditioning equipment is effectively improved on the other hand.

Example two

As shown in fig. 3, in an embodiment of the present invention, the operation control method of the air conditioner further includes:

step S302, acquiring a preset model and acquiring historical operating parameters;

and step S304, generating a corresponding training set according to the historical operating parameters, and training a preset model through the training set to obtain a threshold determination model.

In step S304, the step of generating a corresponding training set according to the historical operating parameters specifically includes, as shown in fig. 4:

step S402, performing data cleaning on historical operating parameters to obtain a noise reduction data set;

and S404, marking the noise reduction data set through a mean shift clustering algorithm to obtain a training set.

The step of performing data cleaning on the historical operating parameters specifically comprises the following steps: sequencing the historical operating parameters to obtain a historical operating parameter sequence; determining a target parameter interval according to the historical operating parameter sequence, acquiring historical operating parameters in the target parameter interval, and determining the historical operating parameters as a first data set; filling the first data set by a hot card filling method to obtain a second data set; and determining the working condition characteristics corresponding to each historical operating parameter in the second data set, acquiring the historical operating parameters corresponding to the working condition characteristics which accord with the preset working condition characteristics in the second data set, and determining the historical operating parameters as a noise reduction data set.

The method comprises the following steps of marking a noise reduction data set through a mean shift clustering algorithm, and specifically comprises the following steps: selecting any historical operating parameter from the noise reduction data set, and determining the parameter as first initial central data; acquiring a preset kernel function and an updating function, and acquiring a function bandwidth corresponding to the preset kernel function; calculating a first offset mean value corresponding to the first initial central data through a preset kernel function, and identifying the size relation between the first offset mean value and a preset offset threshold value; determining that the first deviation mean value is larger than or equal to a preset deviation threshold value, determining second initial central data through an updating function, determining a second deviation mean value corresponding to the second initial central data through a preset kernel function, and determining the second central data as central data until the second deviation mean value is smaller than the preset deviation threshold value; and determining a target data category to which the central data belongs, and marking the historical operating parameters with the difference value smaller than or equal to the function bandwidth with the central data as the target data category.

The historical operating parameters include a compressor current load rate of the air conditioning unit, and at least one of: the running state of a water chilling unit of the air conditioning equipment, the outlet water temperature of cooling water of the air conditioning equipment, the inlet water temperature of the cooling water of the air conditioning equipment, the outlet water temperature of chilled water of the air conditioning equipment and the return water temperature of the chilled water of the air conditioning equipment.

In the embodiment, the threshold determination model is obtained by training the artificial intelligence model through big data, and the accuracy of the generated target threshold is improved in the subsequent control process. Specifically, historical operating parameters can be obtained from a database, wherein the historical operating parameters comprise a large number of operating parameters of the air conditioner under different configurations, different use scenes and different working condition environments, the operating parameters are processed to generate corresponding training sets, and the preset models are trained through the training sets, so that the finally obtained threshold value determination models are more accurate, and the operation control effect of the air conditioning equipment is improved.

Because the historical operating parameters may include operating data in an abnormal state, such as operating data during a fault of air conditioning equipment, null shift data generated by a sensor, data loss generated in a network transmission process, and the like, in order to improve the accuracy of the threshold determination model, data cleaning needs to be performed on the historical operating parameters, and specifically, data cleaning can be performed by a big data cleaning method to remove noise data in the data. Meanwhile, after the noise reduction data set is obtained, the noise reduction data set is marked through a mean shift clustering algorithm, a training set for training a preset model can be obtained, the accuracy of the threshold value determination model can be effectively improved through training the preset model through the training set, and further the operation control effect of the air conditioning equipment is improved.

The data cleaning of the historical operating parameters can be divided into the following steps:

first, outlier culling is performed. Specifically, the historical operating parameters of the same category are sorted according to the numerical value, the operating parameter sequence arranged according to the numerical value is obtained, the target parameter interval is determined according to the operating parameter sequence, the upper quartile value and the lower quartile value of the operating parameter sequence can be calculated, the upper quartile value and the lower quartile value serve as boundary values to determine the upper boundary and the lower boundary of the target parameter interval, and when the operating parameters exceed the upper boundary and the lower boundary of the target parameter interval, data abnormality is judged. In the operation process, conditions such as system faults, sensor drift and the like can possibly cause abnormal large values and abnormal small values of operation parameters, so that after the data are removed, a first data set of the operation parameters which can reflect normal operation conditions can be obtained.

Wherein, the condition of presetting the operating mode is: the difference between the inlet water temperature of the chilled water and the return water temperature of the chilled water is greater than or equal to 2 ℃.

In the process of marking the noise reduction data set by the mean shift clustering algorithm, the preset kernel function can be processed by adopting a three-dimensional kernel function such as a Gaussian kernel function. Specifically, a historical operating parameter is selected from the noise reduction data set as first initial central data, a function bandwidth of a preset kernel function is used as a radius, a set of the historical operating parameter is divided, and a first deviation mean value corresponding to the first central data is determined according to the set of the historical operating parameter. The first deviation mean value can reflect the difference between the first initial central data and other historical operating parameters, and the larger the first deviation value, the farther the first initial central data is from the actual data "center".

The historical operation parameters comprise the current load rate of a compressor of the air conditioning equipment, the operation state of a water chilling unit of the air conditioning equipment, the outlet water temperature of cooling water of the air conditioning equipment, the inlet water temperature of the cooling water of the air conditioning equipment, the outlet water temperature of chilled water of the air conditioning equipment, the return water temperature of the chilled water of the air conditioning equipment and the like.

It will be appreciated that as air conditioners are improved and as actually installed, the historical operating parameters may also include any other operating parameters that may be obtained for the operation of the air conditioner.

In some embodiments, the predetermined kernel function is:

K(x_i-x)；

and is optionally a gaussian kernel function. The kernel function is used to determine the weights of the neighbors of x, which are used to recalculate the mean.

The shifted mean of the x points can be expressed as:

wherein N (x) is a neighbor set of xi, K (x)_i-x) is a given function, x is center point data, x_iFor data corresponding to any point in the set M other than the center point x, M_h(x) Is a shifted mean.

The update function is:

x^t+1＝x^t+M_h(x)；

wherein x is^tIs the current center point, x^t+1Is the next center point, M_h(x) Is a shifted mean.

EXAMPLE III

In an embodiment of the present invention, an air conditioning apparatus of a water chiller is taken as an example to specifically describe the embodiment of the present invention:

the embodiment of the invention mainly comprises two parts of model establishment and load/unload control conditions of a set dynamically regulated by a model, and the method comprises the following specific steps:

firstly, applying a big data cleaning method to the pretreatment of original data of a BMS database to obtain a data set of a stable operation condition of a water chilling unit;

secondly, self-adaptive classification is carried out on the current load rate of the water chilling unit by adopting a Mean-Shift clustering algorithm (Mean-Shift), and the characteristics of the current load rate of the water chilling unit under different operating conditions are mined;

thirdly, respectively adopting a least square method to the maximum class and the minimum class to obtain a threshold model of the current load rate of the water chilling unit according to the current load rate clustering result of the unit;

fourthly, providing a current judgment condition for unit load and unload control according to the current load rate threshold model of the water chilling unit and the real-time operation data of the unit;

and fifthly, establishing a loading and unloading control strategy of the water chilling unit by combining the current judgment condition and the water temperature judgment condition.

Specifically, in the first point, the BMS system collects operation data of the chiller in real time through various sensors installed in the freezer room and stores the data in a history database. The water chilling unit operation parameters required to be extracted by the invention comprise:

the running state of the water chilling unit, the outlet water temperature of cooling water, the inlet water temperature of cooling water, the outlet water temperature of chilled water, the return water temperature of chilled water and the current load rate of the unit. For a water chilling unit adopting double machine heads, the current load rates of the two machine heads are selected, and the average value is taken for analysis.

In the second point, outlier data is caused because the sensors often produce zero drift data. The local area network often has data transmission signal loss, resulting in more data loss, and the BMS collected data inevitably has noise, missing data and abnormal values, and needs to adopt a data preprocessing technology to preprocess the original data. The pretreatment method adopted in the embodiment comprises the following steps: abnormal value elimination, missing data supplement and stable working condition screening.

And (4) removing abnormal values, namely removing the running data of the water chilling unit in the BMS database when the water chilling unit is not started. Secondly, acquiring the upper quartile and the lower quartile of each parameter according to the historical normal operation data of the unit by adopting a boxplot analysis method: including Q3 (upper quartile) and Q1 (lower quartile), and calculate the quartile distance: IQR ═ Q3-Q1, and the upper and lower bounds of the parameters were obtained:

L_up＝Q3+1.5×IQR，L_low＝Q1-1.5×IQR。

wherein L is_upIs an upper boundary, L_lowFor the lower boundary, Q3 is the upper quartile, Q1 is the lower quartile, and IQR is Q3-Q1.

Judging whether each operation parameter obtained from the BMS database is located in the upper and lower boundary ranges, if so, retaining the data; if not, the abnormal value is eliminated.

And a step of supplementing the missing value, which can adopt a Hot card filling method (Hot deck), find a data corresponding to the working condition closest to the current missing data in the unit historical operation database, and then supplement the missing data by using the corresponding data of the similar working condition.

The purpose of stable condition screening is in order to get rid of the unstable data that cooling water set produced at the start-stop in-process, avoids causing the precision decline of COP regression model, and stable condition judgement condition is: the inlet temperature of the chilled water-the return temperature of the chilled water is more than or equal to 2 ℃.

In the third point, the current load rate of the water chilling unit is self-adaptively classified by Mean-Shift Cluster, and the Cluster parameters are the current load rate of the unit and the water inlet temperature of cooling water. The reason for selecting the inlet water temperature of the cooling water as the clustering parameter is as follows: the size of the inlet water temperature of the cooling water directly influences the condensation temperature of the water chilling unit, so that the power consumption of the unit is influenced.

Mean-shift clustering first assumes that each cluster in the sample space obeys some known probability distribution rule, then fits a statistical histogram in the sample with different probability density functions, and continuously shifts the position of the center of the density function until the best fit is obtained. The peak point of the probability density functions is the center of the cluster, and then the category to which the nearest cluster center belongs is selected as the category of the sample according to the distance between each sample and each center.

The specific mean shift clustering steps are as follows:

step 3-1: randomly selecting a point from the unmarked data points as a center x, wherein the radius is the kernel function bandwidth h, and recording a point set M in the radius h, wherein the points in the set M all belong to a cluster C.

Step 3-2: given a kernel function K (x)_i-x) and optionally a gaussian kernel function. The kernel function is used to determine the weights of the neighbors of x, which are used to recalculate the mean.

The shifted mean of the x points can be expressed as:

wherein N (x) is a neighbor set of xi, K (x)_i-x) is a given function, x is center point data, x_iFor data corresponding to any point in the set M other than the center point x, M_h(x) Is the shifted mean of the x points.

Step 3-3: judging whether the deviation mean value is smaller than a threshold value: i M_h(x)||<If yes, ending iteration; if not, updating the position of the center according to the following formula:

x^t+1＝x^t+M_h(x)；

Step 3-4: if the distance between the center point of the current cluster C and the center of other existing clusters is less than epsilon during convergence, the two clusters are merged into one class, otherwise, one class is added.

Step 3-5: the above steps are repeated until all points are marked.

In the fourth point, the maximum class and the minimum class can be found according to the current load rate clustering result, the current load rate clustering result and the current load rate of each clustering center. And in the maximum class, acquiring a maximum current load rate value set corresponding to different cooling water inlet temperatures, processing the maximum value set by adopting a box chart method, and removing deviation points. And then performing least square regression on the processed maximum current load rate value to obtain a current load rate upper boundary model, namely a maximum threshold model. Similarly, a lower boundary model of the current load factor, i.e., a minimum threshold model, may be obtained according to the minimum class. Along with the operation of the water chilling unit, the BMS database continuously updates the operation data of the water chilling unit, the unit operation data (the initial time + delta t and the termination time + delta t of the data) are called from the BMS historical database at regular intervals delta t, and the least square regression is carried out on the threshold model of the current load rate again to achieve the accuracy of the model.

In the fifth point, the chiller unit loading strategy specifically includes:

(1) BMS (battery management system) acquisition chilled water outlet temperature T_chw,out,iAnd return temperature T of chilled water_chw,in,iJudgment of T_chw,out,i-T_chw,out,set>2 ℃ and T_chw,in,i-T_chw,out,i>If one of the temperature ranges of 6 ℃ is met, entering a judgment condition (2) if the temperature is met; if not, the loading strategy is not executed;

(2) BMS (battery management system) acquisition cooling water inlet temperature T_cw,in,iSum current load rate LR_iCalculating the maximum current load rate LR corresponding to the current working condition according to the current load rate upper boundary model_max,iAnd determining LR_i≥LR_max,iIf yes, delaying for 20min to prepare to execute the loading strategy; if not, returning to the judgment condition (1);

(3) and only when the conditions (1) and (2) continuously meet the requirements within 20min, the unit is loaded.

The water chilling unit load shedding strategy specifically comprises the following steps:

(1) BMS (battery management system) acquisition chilled water outlet temperature T_chw,out,iAnd return temperature T of chilled water_chw,in,iJudgment of T_chw,out,set-T_chw,out,i<2 ℃ and T_chw,in,i-T_chw,out,i<Whether the temperature is satisfied at 3.5 ℃ or not, if yes, entering a judgment condition (2); if not, the load shedding strategy is not executed;

(2) BMS (battery management system) acquisition cooling water inlet temperature T_cw,in,iSum current load rate LR_iAnd calculating the minimum current load rate LR corresponding to the current working condition according to the current load rate lower boundary model_min,iAnd determining LR_i≤LR_min,iIf yes, delaying for 20min to prepare to execute a load shedding strategy; if not, returning to the judgment condition (1);

(3) and only when the conditions (1) and (2) continuously meet the requirements within 20min, the load of the unit is reduced.

The following is a specific embodiment of the present invention:

the flow of the self-adaptive load increase and decrease control method of the central air conditioning water chilling unit based on big data analysis is shown in figure 5:

step S502, BMS implements data collection;

step S504, establishing a BMS historical database;

step S506, preprocessing data;

step S508, gathering current load rates of the water chilling unit;

step S510, establishing a current load rate threshold model;

step S512, determining a current load factor judgment condition;

step S514, determining a judgment condition of the temperature of the chilled water;

and step S516, determining a loading and unloading strategy of the water chilling unit.

Wherein, for BMS raw data acquisition:

the method comprises the steps of collecting relevant operation parameters of the water chilling unit through a BMS system, wherein the relevant operation parameters comprise the unit operation state, the cooling water outlet temperature, the cooling water inlet temperature, the chilled water outlet temperature, the chilled water return temperature and the unit current load rate. Because the double-head water chilling unit can respectively output the current load rates of the two heads, the average value is taken for analysis.

For data preprocessing:

since sensors often produce null drift data, outlier data results. The local area network often has data transmission signal loss again, leads to the data to lack more, and BMS data collection inevitably has noise, missing value and outlier, needs to adopt data preprocessing technique to wash the original data. The cleaning method mainly comprises the steps of abnormal value elimination, missing value supplement and stable working condition screening.

Removing data points with the running state of 0 of the water chilling unit by the abnormal value removing; and secondly, removing abnormal values deviating from the normal operation state for each operation parameter of the water chilling unit by adopting a box chart method. Acquiring the upper quartile and the lower quartile of each parameter from BMS historical data: q3, Q1.

Calculating the four-bit distance: IQR-Q3-Q1, resulting in upper and lower bounds of the parameter:

L_up＝Q3+1.5×IQR，L_low＝Q1-1.5×IQR。

Judging whether each operation parameter obtained from the BMS database is located in the upper and lower boundary ranges, if so, retaining the data; if not, the abnormal value is eliminated. And the missing value is supplemented by a hot card filling method. And if certain parameter acquired by the BMS is missing at a certain moment, searching a working condition closest to the current missing value from the historical database by using the hot card filling method, and then supplementing the missing value by using the corresponding value of the similar working condition.

The judgment conditions for stable working condition screening are as follows: and the inlet water temperature of the chilled water and the return water temperature of the chilled water are more than or equal to 2 ℃, if BMS read data meet the condition, the data are retained, and if the BMS read data do not meet the condition, the data are rejected as unstable working conditions. The unstable operation condition data of the unit in a period of time after the unit is started can be eliminated by using the judgment condition.

For current load rate clustering:

in order to find the boundary model of the current load rate of the water chilling unit, the operation condition of the water chilling unit needs to be subjected to cluster analysis, and the water inlet temperature of cooling water and the current load rate of the unit are selected as cluster parameters. The reason for selecting the inlet water temperature of the cooling water as the clustering parameter is as follows: the size of the inlet water temperature of the cooling water directly influences the condensation temperature of the water chilling unit, so that the power consumption of the unit is influenced. The Mean-Shift clustering algorithm (Mean-Shift) based on kernel density estimation can obtain a data distribution mode through fast iterative computation, automatically determine the number of clusters and trace out the boundaries of the clusters, and therefore, the Mean-Shift clustering algorithm is widely applied to a big data analysis process. Mean-shift clustering first assumes that each cluster in the sample space obeys some known probability distribution rule, then fits a statistical histogram in the sample with different probability density functions, and continuously shifts the position of the center of the density function until the best fit is obtained. The peak point of the probability density functions is the center of the cluster, and then the category to which the nearest cluster center belongs is selected as the category of the sample according to the distance between each sample and each center. The principle of mean-shift clustering is shown in fig. 6.

First, as shown in fig. 6, a point is randomly selected as a center x from among the unmarked data points, the radius is the kernel bandwidth h, and a set M of points within the radius h is recorded, the points belonging to the cluster C.

Second, given a kernel function K (xi-x), a Gaussian kernel function is typically employed. The kernel function is used to determine the weights of the neighbors of x, which are used to recalculate the mean. The mean shift at point x can be expressed as:

given a kernel function K (x)_i-x) and optionally a gaussian kernel function. The kernel function is used to determine the weights of the neighbors of x, which are used to recalculate the mean.

The shifted mean of the x points can be expressed as:

Then, whether the offset mean is smaller than a threshold is judged: i M_h(x)||<If yes, ending iteration; if not, updating the position of the center according to the following formula:

x^t+1＝x^t+M_h(x)；

If the distance between the center point of the current cluster C and the center of other existing clusters is less than epsilon during convergence, the two clusters are merged into one class, otherwise, one class is added.

Finally, the above steps are repeated until all points are marked.

For determining the chiller current load rate boundary model:

according to the current load rate clustering result and the current load rate of each clustering center, the maximum class and the minimum class can be found. And in the maximum class, acquiring a maximum current load rate value set corresponding to different cooling water inlet temperatures, processing the maximum value set by adopting a box chart method, and removing deviation points. And performing least square regression on the processed maximum current load rate value to obtain a current load rate upper boundary model. And similarly, in the minimum class, acquiring a minimum current load rate value set corresponding to different cooling water inlet temperatures, processing the minimum value set by adopting a box chart method, and removing deviation points. And performing least square regression on the processed minimum current load rate value to obtain a lower boundary model of the current load rate. By solving a threshold model of the current load rates of 4 water chilling units, the water inlet temperature of cooling water can be collected in real time according to the BMS, the upper limit extreme value and the lower limit extreme value of the current load rate of the units are determined, and whether the units need to be loaded or unloaded is judged according to the current load rate of the units read by the BMS.

With the operation of the water chilling unit, the BMS continuously collects the operation data of the water chilling unit and updates the historical database of the water chilling unit, and in order to ensure that the current load rate threshold model can track and reflect the real operation state of the water chilling unit, an adaptive regression method is needed to iteratively update the fitting coefficient of the model. Namely, the operation data of the unit is called from the BMS historical database at regular time intervals delta t (calling data starting time + delta t, and ending time + delta t), and least square regression is carried out on the current load rate upper and lower threshold models again to achieve the accuracy of the models.

For the water chilling unit load and unload control strategy:

The load shedding strategy of the water chilling unit is as follows:

(2) BMS (battery management system) acquisition cooling water inlet temperature T_cw,in,iSum current load rate LR_iCalculating the maximum corresponding to the current working condition according to the current load rate lower boundary modelLow current load rate LR_min,iAnd determining LR_i≤LR_min,iIf yes, delaying for 20min to prepare to execute a load shedding strategy; if not, returning to the judgment condition (1);

The complete control logic diagram is shown in fig. 7:

step S702, BMS implements data collection;

step S704, detecting the running state of the water chilling unit;

step S706, judging whether T is satisfied_chw,out,i-T_chw,out,set>2 ℃ or T_chw,in,i-T_chw,out,i>6 ℃; if yes, go to step S710, otherwise go to step S708;

step S708, the host does not act;

step S710, determining a current load factor maximum threshold model;

step S712, determining the current maximum current load rate LR_max：

Step S714, judge whether LR > LR is satisfied_max(ii) a If yes, go to step S716, otherwise return to step S708;

step S716, delaying for 20min, and loading by the host;

step S718, determine whether T is satisfied_chw,out,set-T_chw,out,i<2 ℃ and T_chw,in,i-T_chw,out,i<3.5 ℃; if yes, go to step S720, otherwise go to step S708;

step S720, determining a current load factor minimum threshold model;

step S722, determining the current minimum current load rate LR_min；

Step S724 judges whether LR < LR is satisfied_min(ii) a If yes, go to step S726, otherwise return to step S708;

and step S726, delaying for 20min, and unloading the host.

The following is a specific data analysis:

the following data come from a central air-conditioning cold source system of a certain office building, wherein the central air-conditioning system is provided with 4 water chilling units, wherein 3 water chilling units are 550RT centrifugal water chilling units, and 1 screw water chilling unit is 370RT, and the running data of the water chilling units for 3 months is selected for analysis.

First, the operating data of 4 chiller units for 2 months was read from the BMS database and the raw data was preprocessed. On the basis of the processed data, the current load rate of the unit and the water inlet temperature of the cooling water are taken as clustering parameters, the operation condition parameters of 4 water chilling units are clustered by mean shift clustering, and the clustering result is shown in fig. 8.

In fig. 8, the hollow dot is the cluster center of each category, and represents the point of maximum density of data points in the category. The operation conditions of the units 1 to 3 are divided into 2 types, the operation conditions of the unit 4 are divided into 3 types, and the classification is based on the current load rate of the units and is unrelated to the inlet water temperature of cooling water. The clustering boundary of the current load rates of the unit 1 and the unit 2 is about 70%, the clustering boundary of the current load rates of the unit 3 is about 80%, and the clustering boundary of the current load rates of the unit 4 is about 62% and 80%.

For each water chilling unit, an extreme value set in the class with the largest current load rate and an extreme value set in the class with the smallest current load rate are searched, and after the extreme value sets are processed by a box type graph method, least square regression is respectively performed, so that a threshold model of each unit is obtained, as shown in fig. 9.

In fig. 9, the maximum and minimum threshold models of the unit 1 are respectively:

LR_max,1＝0.377×T_cw,in+74.835，(T_cw,in∈[15，35])；

LR_min,1＝0.653×T_cw,in+44.375，(T_cw,in∈[15，35])；

the maximum and minimum threshold models of the unit 2 are respectively:

LR_max,2＝1.120×T_cw,in+61.375，(T_cw,in∈[15，35])；

LR_min,2＝0.607×T_cw,in+46.496,(T_cw,in∈[15，35])；

the maximum and minimum threshold models of the unit 3 are respectively:

LR_max,3＝0.793×T_cw,in+76.285，(T_cw,in∈[15，35])；

LR_min,3＝0.417×T_cw,in+47.134，(T_cw,in∈[15，35])；

the maximum and minimum threshold models of the unit 4 are respectively:

LR_max,4＝1.669×T_cw,in+44.794，(T_cw,in∈[15，35])；

LR_min,4＝37.5，(T_cw,in∈[15，35])；

wherein, T_cw,inFor cooling water inlet temperature, LR_max,1To LR_max,4Upper boundaries, LR, corresponding to the units 1 to 4, respectively_min,1To LR_min,4Respectively, the lower boundaries corresponding to the units 1 to 4.

As can be seen from fig. 9, the slopes of the upper and lower current load rate boundary models of each chiller are all greater than 0, except for the lower boundary model of the unit 4, which indicates that the unit current load rate tends to increase with the increase of the cooling water inlet temperature.

On the basis of obtaining 4 cooling water set current load rate boundary models, the BMS judges whether the current running set reaches the condition of adding or subtracting the machine according to the set running data collected in real time. As shown in fig. 3, in the case where a plurality of water chiller units are operated in combination, the BMS determines whether the water chiller units are under load or not by detecting the operation data of the water chiller units that are started after the detection. The loading and unloading control logic of the water chilling unit is divided into loading logic and unloading logic, in the loading logic, only if the judgment condition of chilled water temperature and the judgment condition of current load rate are simultaneously met, and the judgment condition is not changed within 20min, the loading control is carried out on the water chilling unit, and one water chilling unit is newly started; in the load shedding logic, only if the judgment conditions of the chilled water temperature and the current load rate are met at the same time and the judgment conditions are unchanged within 20min, the load shedding control is carried out on the unit, and the last water chilling unit is closed.

Example four

As shown in fig. 10, in one embodiment of the present invention, there is provided an operation control system 1000 of an air conditioner including: a memory 1002 configured to store a computer program; the processor 1004 is configured to execute a computer program to implement the operation control method of the air conditioning equipment provided in any of the above embodiments, and therefore, the operation control system 1000 of the air conditioning equipment includes all the beneficial effects of the operation control method of the air conditioning equipment provided in any of the above embodiments, which are not described herein again.

EXAMPLE five

In one embodiment of the present invention, there is provided an air conditioning apparatus including: the water cooling units comprise compressors, cooling water pipes, heat exchangers and throttling devices; the detection device is configured to acquire the current load rate of the compressor, acquire the water inlet temperature and the water outlet temperature of the cooling water pipe and acquire the water inlet temperature and the water outlet temperature of the freezing water pipe; in the operation control system of the air conditioning equipment provided in any one of the above embodiments, the operation control system of the air conditioning equipment is connected with the water chiller unit and the detection device. Therefore, the overall beneficial effects of the operation control system of the air conditioner including the air conditioner provided in any one of the above embodiments are not described herein.

EXAMPLE six

In an embodiment of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the operation control method of the air conditioning equipment provided in any one of the above embodiments, and therefore, the computer-readable storage medium includes all the beneficial effects of the operation control method of the air conditioning equipment provided in any one of the above embodiments, and is not described herein again.

In the description of the present invention, the terms "plurality" or "a plurality" refer to two or more, and unless otherwise specifically defined, the terms "upper", "lower", and the like indicate orientations or positional relationships based on the orientations or positional relationships illustrated in the drawings, and are only for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention; the terms "connected," "mounted," "secured," and the like are to be construed broadly and include, for example, fixed connections, removable connections, or integral connections; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.

In the description of the present invention, the description of the terms "one embodiment," "some embodiments," "specific embodiments," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In the present invention, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An operation control method of an air conditioning apparatus, characterized by comprising:

acquiring the operating parameters of the air conditioning equipment;

inputting the operation parameters into a threshold determination model to obtain target thresholds corresponding to the operation parameters;

determining a corresponding operation instruction according to the operation parameter and the target threshold value, and controlling the air conditioning equipment to execute the operation instruction;

the operation parameters comprise the current load rate of the air conditioning equipment, and the target threshold comprises a maximum load rate threshold and a minimum load rate threshold corresponding to the current load rate;

the step of determining the corresponding operation instruction according to the operation parameter and the target threshold specifically includes:

identifying a magnitude relationship of the current loading rate to the maximum loading rate and the minimum loading rate;

identifying that the current load rate is greater than or equal to the maximum load rate threshold, determining that the operating instruction is a load operation;

identifying that the current load rate is less than or equal to the minimum load rate threshold, determining that the operating command is a load shedding operation;

the operation parameters further comprise the inlet water temperature of cooling water of the air conditioning equipment and the outlet water temperature of chilled water, and the target threshold further comprises a first difference threshold, a second difference threshold and a third difference threshold;

before the step of identifying the magnitude relationship between the current load rate and the maximum load rate and the minimum load rate, the operation control method further includes;

acquiring a set water outlet temperature;

calculating a first difference value between the water outlet temperature and the set water outlet temperature, and calculating a second difference value between the water inlet temperature and the water outlet temperature;

determining that an absolute value of the first difference is greater than the first difference threshold or the second difference is greater than the second difference threshold; or

Determining that the absolute value of the first difference is less than the first difference threshold and the second difference is less than the third difference threshold, performing the step of identifying the magnitude relationship of the current share to the maximum share and the minimum share.

2. The operation control method of an air conditioning apparatus according to claim 1, characterized by further comprising:

and acquiring a setting instruction, and determining the first difference threshold, the second difference threshold and the third difference threshold according to the setting instruction.

3. The operation control method of an air conditioning apparatus according to claim 1 or 2, characterized by further comprising:

acquiring a preset model and acquiring historical operating parameters;

and generating a corresponding training set according to the historical operating parameters, and training the preset model through the training set to obtain the threshold determination model.

4. The operation control method of the air conditioning equipment according to claim 3, wherein the step of generating the corresponding training set according to the historical operation parameters specifically includes:

performing data cleaning on the historical operating parameters to obtain a noise reduction data set;

and marking the noise reduction data set through a mean shift clustering algorithm to obtain the training set.

5. The operation control method of the air conditioning equipment according to claim 4, wherein the step of performing data washing on the historical operation parameters specifically comprises:

sequencing the historical operating parameters to obtain a historical operating parameter sequence;

determining a target parameter interval according to the historical operating parameter sequence, acquiring the historical operating parameters in the target parameter interval, and determining the historical operating parameters as a first data set;

filling the first data set by a hot card filling method to obtain a second data set;

and determining the working condition characteristics corresponding to each historical operating parameter in the second data set, acquiring the historical operating parameters corresponding to the working condition characteristics which accord with preset working condition characteristics in the second data set, and determining the historical operating parameters as the noise reduction data set.

6. The operation control method of the air conditioning equipment according to claim 4, wherein the step of labeling the noise reduction data set by a mean shift clustering algorithm specifically comprises:

selecting any one of the historical operating parameters in the noise reduction data set, and determining the selected historical operating parameter as first initial central data;

acquiring a preset kernel function and an updating function, and acquiring a function bandwidth corresponding to the preset kernel function;

calculating a first offset mean value corresponding to the first initial central data through the preset kernel function, and identifying the size relation between the first offset mean value and a preset offset threshold value;

determining that the first deviation mean value is greater than or equal to the preset deviation threshold value, determining second initial central data through the updating function, determining a second deviation mean value corresponding to the second initial central data through the preset kernel function, and determining the second initial central data as central data until the second deviation mean value is smaller than the preset deviation threshold value;

and determining a target data category to which the central data belongs, and marking the historical operating parameters with the difference value smaller than or equal to the function bandwidth with the central data as the target data category.

7. The operation control method of an air conditioning apparatus according to claim 3, wherein the historical operation parameter includes a compressor current load rate of the air conditioning apparatus, and at least one of:

the air conditioner comprises an air conditioning device, a water chilling unit, a cooling water outlet temperature, a cooling water inlet temperature, a chilled water outlet temperature and a chilled water return temperature, wherein the air conditioning device comprises a water chilling unit, a water chilling unit and a water cooling unit.

8. An operation control system of an air conditioning apparatus, characterized by comprising:

a memory configured to store a computer program;

a processor configured to execute the computer program to implement the operation control method of the air conditioning apparatus according to any one of claims 1 to 7.

9. An air conditioning apparatus, characterized by comprising:

the system comprises a plurality of water cooling units, a plurality of water cooling units and a control unit, wherein each water cooling unit comprises a compressor, a cooling water pipe, a freezing water pipe, a heat exchanger and a throttling device;

the detection device is configured to acquire the current load rate of the compressor, acquire the water inlet temperature and the water outlet temperature of the cooling water pipe, and acquire the water inlet temperature and the water outlet temperature of the freezing water pipe;

the operation control system of an air conditioner according to claim 8, which is connected to the water chiller unit and the detection device.

10. A computer-readable storage medium on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements a control method of an air conditioning apparatus according to any one of claims 1 to 7.